-.TH lfs_migrate 1 "Jul 21, 2010" Lustre "utilities"
+.TH lfs_migrate 1 "Dec 19, 2017" Lustre "utilities"
.SH NAME
.B lfs_migrate
-\- simple tool to migrate files between Lustre OSTs
+\- migrate files between Lustre OSTs
.SH SYNOPSIS
.B lfs_migrate
-.RB [ -c <stripe_count> ]
-.RB [ -h ]
-.RB [ -l ]
-.RB [ -n ]
-.RB [ -q ]
-.RB [ -R ]
-.RB [ -s ]
-.RB [ -y ]
-.RI [ file | "directory ..." ]
+.RB [ "-A " [ -C \fI<cap> \fR] [ -M \fI<min_free> \fR] [ -X \fI<max_free> \fR]]
+.RB [ --dry-run | -n ]
+.RB [ --help | -h ]
+.RB [ --no-rsync | --rsync ]
+.RB [ --quiet | -q ]
+.RB [ --restripe | -R ]
+.RB [ --stripe-count | -c \fI<stripe_count> \fR]
+.RB [ --stripe-size | -S \fI<stripe_size> \fR]
+.RB [ --skip | -s ]
+.RB [ --verbose | -v ]
+.RB [ --yes | -y ]
+.RB [ -D ]
+.RB [ -0 ]
+.RI [ FILE | DIR ] ...
.br
.SH DESCRIPTION
.B lfs_migrate
-is a simple tool to assist migration of files between Lustre OSTs. It
-is simply copying each specified file to a new file, verifying the file
-contents have not changed, and then renaming the new file back to the
-original filename. This allows balancing space usage between OSTs, moving
-files off OSTs that are starting to show hardware problems (though are still
-functional), or OSTs that will be removed from the filesystem.
-.PP
-Because
-.B lfs_migrate
-is
-.B not
-closely integrated with the MDS, it cannot determine whether a file
-is currently open and/or in-use by other applications or nodes. That makes
-it
-.B
-UNSAFE
-for use on files that might be modified by other applications, since the
-migrated file is only a copy of the current file, and this will result in
-the old file becoming an open-unlinked file and any modifications to that
-file will be lost.
+is a tool to assist migration of files between Lustre OSTs, possibly also
+restriping the files as it goes. It copies each specified file to a new file,
+verifies the file contents have not changed, and then replaces the original
+filename with the new file (either atomically via
+.BR lfs-migrate (1)
+on Lustre 2.5 and later, or
+.BR mv (1)
+on older versions of Lustre). This allows balancing space usage between OSTs,
+moving files off OSTs that are starting to show hardware problems but are still
+functional, or OSTs that will be removed from the filesystem.
.PP
Files to be migrated can be specified as command-line arguments. If a
directory is specified on the command-line then all files within that
then a list of files is read from the standard input, making
.B lfs_migrate
suitable for use with
-.BR lfs (1) " find"
-to locate files on specific OSTs and/or matching other file attributes.
+.BR lfs-find (1)
+to locate files on specific OSTs and/or matching other file attributes,
+or any other tools that generate a list of files.
+.PP
+Any options and arguments not explicitly recognized by
+.B lfs_migrate
+are passed through to the underlying
+.B lfs migrate
+command, see
+.BR lfs-migrate (1)
+and
+.BR lfs-setstripe (1)
+for a complete list of options.
+.PP
+To maintain backward compatibility, the \fI-n \fRoption is used by the
+script to indicate a dry-run (no modifications made), and is not passed to
+.B lfs migrate
+as the non-block option. To specify non-block, use the long option
+.BR --non-block .
.PP
The current file allocation policies on MDS dictate where the new files
are placed, taking into account whether specific OSTs have been disabled
or OST index of a new file).
.SH OPTIONS
.TP
-.B \\-c <stripe_count>
-Restripe file using the specified stripe count. This option may not be
-specified at the same time as the -R option.
+.B \\--dry-run|-n
+Only print the names of files to be migrated.
+.TP
+.B \\-D
+Do not use direct I/O to copy file contents.
+.TP
+.B \\-A
+Automatically determine the stripe count for the file, using the algorithm
+count = sqrt(filesize_in_GB) + 1. This option may not be specified at the
+same time as the \fB-c \fRor \\-R \fRoptions.
.TP
-.B \\-h
+.B \\--stripe-count|-c \fI<stripe_count>
+Restripe file using the specified \fIstripe_count\fR. This option may not be
+specified at the same time as the \fB-A \fRor \fB-R \fRoptions.
+.TP
+.B \\-C \fI<cap>
+When \fB-A \fRis set, limit the migrated file to use on each OST at most
+1/\fIcap \fRof the available space of the smallest OST. If this option is not
+set, a default value of 100 is used, limiting the object size to 1% of available
+space.
+.TP
+.B \\--help|-h
Display help information.
.TP
-.B \\-l
-Migrate files with hard links (skip by default). Files with multiple
-hard links will be split into multiple separate files by
-.B lfs_migrate
-so they are skipped by default to avoid breaking the hard links.
+.B \\--no-rsync
+Do not fall back to using rsync if
+.BR lfs-migrate (1) " fails."
+Cannot be used at the same time as \fB--rsync\fR.
+.B \\--min-free|-M \fI<min_free>
+When \fB-A \fRis set, only consider OSTs with free space greater than the
+\fImin_free \fRvalue to be available for migration. The value is specified in
+KB. If this option is not set, a default of 256MB is used.
.TP
-.B \\-n
-Only print the names of files to be migrated
+.B \\--quiet|-q
+Run quietly (don't print filenames or status).
.TP
-.B \\-q
-Run quietly (don't print filenames or status)
+.B \\--rsync
+Force rsync to be used instead of
+.BR lfs-migrate (1) .
+May not be used at the same time as
+.BR --no-rsync .
.TP
-.B \\-R
+.B \\--restripe|-R
Restripe file using default directory striping instead of keeping striping.
-This option may not be specified at the same time as the -c option.
+This option may not be specified at the same time as the \fB-A\fR, \fB-c\fR, or
+\fB-S \fRoptions. (these options are passed through to
+.BR "lfs migrate" ,
+and are therefore not listed here).
.TP
-.B \\-s
-skip file data comparison after migrate. Default is to compare migrated file
+.B \\--skip|-s
+Skip file data comparison after migrate. Default is to compare migrated file
against original to verify correctness.
.TP
-.B \\-y
+.B \\--verbose|-v
+Show verbose debug messages.
+.B \\--max-free|-X \fI<max_free>
+When \fB-A \fRis set, \fImax_free \fRis the maximum amount of free space that
+can be considered available for the migration of the file on each OST. The
+value is specified in KB. This option is useful for testing, by simulating
+OSTs that are nearly full.
+.TP
+.B \\--yes|-y
+Answer 'y' to usage warning without prompting (for scripts; use with caution).
+.SH EXAMPLES
+To rebalance all files within
+.I /testfs/jobs/2011
+.B \\--stripe-size|-S
+.I <stripe_size>
+Restripe file using the specified stripe size. This option may not be
+specified at the same time as the \fB-R \fRoption.
+.TP
+.B \\--yes|-y
Answer 'y' to usage warning without prompting (for scripts, use with caution).
+.TP
+.B \\-0
+Input file names on stdin are separated by a null character.
.SH EXAMPLES
To rebalance all files within
-.IR /mnt/lustre/dir :
+.I /testfs/jobs/2011
+(which are known not to be modified by in-use programs):
.IP
-lfs_migrate /mnt/lustre/dir
+lfs_migrate /testfs/jobs/2011
.PP
To migrate files within the
-.I /test
-filesystem on OST0004 larger than 4GB in size:
+.I /testfs
+filesystem on OST0004 (perhaps because it is much more full than other OSTs),
+larger than 4GB (because it is more efficient to just migrate large files),
+and older than two days (to avoid files that are in use, though this is NOT
+a guarantee the files are not being modified, that is workload specific) after
+disabling file creation on testfs-OST0004 (this is needed on all MDS nodes):
.IP
-lfs find /test -obd test-OST0004 -size +4G | lfs_migrate -y
-.SH KNOWN BUGS
-Hard links could be handled correctly in Lustre 2.0 by using
-.BR lfs (1) " fid2path" .
-.PP
-Eventually, this functionality will be integrated into
-.BR lfs (1)
-itself and will integrate with the MDS layout locking to make it safe
-in the presence of opened files and ongoing file IO.
+.nf
+mds# lctl set_param osp.testfs-OST0004*.max_create_count=0
+client# lfs find /testfs -obd testfs-OST0004 -size +4G -mtime +2d | lfs_migrate -y
+mds# lctl set_param osp.testfs-OST0004*.max_create_count=20000
+.fi
.PP
-Please report all bugs to http://bugzilla.lustre.org/
+To use automatic striping, and limit the object size per OST to 5% of current
+free space:
+.IP
+lfs_migrate -A -C 20 /testfs/jobs/2011
+.SH NOTES
+In versions prior to 2.5,
+.B lfs_migrate
+is
+.B not
+closely integrated with the MDS, and cannot determine whether a file
+is currently open and/or in-use by other applications or nodes. That makes
+it
+.B UNSAFE
+for use on files that might be modified by other applications, since the
+migrated file is only a copy of the current file. This will result in the
+old file becoming an open-unlinked file, and any modifications to that file
+will be lost.
.SH AVAILABILITY
.B lfs_migrate
-is part of the
-.BR Lustre (7)
+is part of the
+.BR Lustre (7)
filesystem package. Added in the 1.8.4 release.
.SH SEE ALSO
.BR lfs (1)
git://git.whamcloud.com / fs / lustre-release.git / blobdiff